Layer 6 · Neuron 7171 · suppressed

L6N7171-1

Word quirks:

“ ⏎”“ ‘”“ ⏎⏎”“⏎”“ ⏎”“ ””“ \"”“ ‘’”

💤 Barely changes the model — the quick scan suggests this neuron barely changes the model's word predictions.

Identity (according to the specimen itself)

Hello! I'm Qwen3.5, a large language model designed to assist with complex reasoning, coding tasks, and multi-step problem-solving. My mission is to empower users by providing accurate, context-aware, and efficient support across diverse domains like science, math, and logic. How can I help you today? 😊

Nearest neighbors

Specimens with similar replies or word quirks. Similarity runs from −1 to 1; 1 is identical. These are leads, not shared mechanisms. How profiles are built.

By word quirks Profile recipe

Specimen	Similarity	Word quirks
1. L9N6182+1🕒	0.99	“ ⏎”“ ‘”“ \"”
2. L10N2890+1💤	0.99	“ ‘’”“ ‘”“ \"”
3. L8N4554+1💤	0.98	“ ‘”“ ⏎”“⏎”
4. L7N5312+1💤	0.97	“⏎”“ ‘”“⏎ ⏎”
5. L3N3413-1💤	0.97	“⏎”“ ‘”“ ⏎”
6. L9N176+1🕒	0.97	“ ⏎”“ ‘”“ ‘’”
7. L7N141-1💤	0.97	“ '”“ ‘”“ \"”
8. L8N6330+1💤	0.97	“⏎”“ ‘”“ \"”
9. L6N7093-1💤	0.97	“ ⏎”“⏎”“ ‘”
10. L7N5455+1💤	0.97	“ ‘”“ ⏎”“ ⏎”

Shadow specimen, apart from the ten: L6N7171+1🕒, -0.18.

Cousins · specimens sharing a neuron

No specimen with replies shares this neuron yet.

Technical details

Quick scan: measure prediction shifts on fixed reference text. Short test: generate replies to a small set of prompts. Longer test: extend to a larger set. Full test: run the full prompt suite. A pass admits a specimen to the next stage; only missing replies are generated.

Layer 6, neuron 7171, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.84, top-1 agreement 0.63) is outside the band that feeds the short test (KL 1 to 2.5, agreement 0.5 to 0.65), so it stays at the quick scan unless someone queues it by hand. A hand pick goes straight to the full test. See Method for the tiers.

Quick scan · prediction measurements

Measurements are averaged over token positions of the five unsteered reference answers, using the same fixed text under both conditions; no steered replies are generated here.

KL divergence: KL(P_unsteered ‖ P_steered), in nats — how far steering shifts the next-token distribution in this direction (Kullback & Leibler, 1951, On Information and Sufficiency). Unsteered ≈ 0.001.
Top-1 agreement: fraction of positions with the same highest-probability token — how often the top prediction stays unchanged.
ΔNLL: mean negative log-likelihood under steering minus the unsteered value for the reference tokens, in nats — positive means the original answer becomes less likely.
Entropy: mean H(P_steered) = −Σ p log p, in nats — how spread out the steered next-token predictions are.

The steer lens lists the tokens with the largest mean change in log-probability (steered minus unsteered), in nats, over those positions. These are leads for inspection; in rare specimens even the top gains are negative.

Setting	KL divergence	Top-1 agreement	ΔNLL	Entropy	Steer lens
L6N7171+1🕒 shadow specimen t0-v0.1	1.949	0.50	2.253	2.02	“ traffic”“ Traffic”“ red”“ signal”“交通”“ lights”“traffic”“红灯”
L6N7171-1 t0-v0.1	0.844	0.63	1.064	1.44	Top boosted tokens ↑

Method

A specimen is a fixed steering configuration of Qwen3.5-4B: one MLP neuron or a pair, each with a signed dose. Unsteered is the control. L identifies the layer; N, the neuron.

Additive activation steering. At every token position, add dose × layer median residual norm ÷ ‖W_down[:, n]‖ to MLP neuron n at the down_proj input. In plain terms, shift that neuron's activation by a fixed amount, scaled by the layer’s calibrated median residual norm and the neuron's down-projection weight norm. Positive doses push up; negative doses push down. Dose is normalized intervention size, not a percentage or probability.